Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

v2.0.0 release - #98

#98
Merged
yqzhishen merged 500 commits into
mainopenvpi/DiffSinger:mainfrom
refactor-v2openvpi/DiffSinger:refactor-v2Copy head branch name to clipboard
Jul 16, 2023
Merged

v2.0.0 release#98
yqzhishen merged 500 commits into
mainopenvpi/DiffSinger:mainfrom
refactor-v2openvpi/DiffSinger:refactor-v2Copy head branch name to clipboard

Conversation

@yqzhishen

@yqzhishen yqzhishen commented Jun 13, 2023 •
edited
Loading

Copy link
Copy Markdown
Member

Resolves #74.

yqzhishen and others added 30 commits April 13, 2023 20:17
@yqzhishen
Adapt VarianceBinarizer to reuse more code
cea94d4
@yqzhishen
Drop 'f0_coarse' from get_pitch_parselmouth
be6311b
@yqzhishen
Merge branch 'refactor-v2' into variance
cf93d62
@yqzhishen
Finish VarianceBinarizer for pitch predictor
d230227
@yqzhishen
Add attributes for pitch predictor to collater
204503f
@yqzhishen
Swap attribute order
57ab513
@yqzhishen
Add back missing norm_spec
24ad74b
@yqzhishen
Merge branch 'refactor-v2' into variance
06e35fe
@hrukalive
Fix typos for validation
51ffa34
@yqzhishen
Merge branch 'refactor-v2' into variance
07aad81
@yqzhishen
Add CurveLoss2d module
dfb3e7d
@yqzhishen
Introduce ph2word, add modules, implement task
76fb972
@yqzhishen
Re-organize variance prediction hparams
2dbe2a9
@yqzhishen
Finish pdur, wdur, sdur losses and lambda
0568bb1
@yqzhishen
Fix key error, dimension error and nan loss
5ae14f2
@yqzhishen
Reuse shape
196dec7
@yqzhishen
Add plot_dur
4868b9b
@yqzhishen
Add alignment dashed lines
7d4c31e
@yqzhishen
Update configs and comments
a5e17c4
@yqzhishen
Add onset embedding
c42f9ae
@yqzhishen
Add casting
ca5752b
@yqzhishen
Add fs2 pitch predictor and pitch plot
9834a08
@yqzhishen
Adapt to diffusion pitch predictor
3bc1dd8
@yqzhishen
Fix TypeError
2e50800
@yqzhishen
Remove keep_bins
5910fcb
@yqzhishen
Adapt wavenet denoiser
1b60a01
@yqzhishen
Add base pitch
81f37aa
@yqzhishen
Reuse wavenet, add 1d diffusion
c271059
@yqzhishen
Clamp curve
a46977f
@yqzhishen
Change color
b7b927f
yqzhishen added 27 commits July 2, 2023 21:31
@yqzhishen
Fix element replacing bug
1eaa2ca
@yqzhishen
Fix missing mel2ph when not training duration predictor
21de5a1
@yqzhishen
Change variance retaking masks from zero inputs to zero embeddings (#104
782f004 
)

* Change variance retaking from zero inputs to zero embeddings

* Support separate variance retaking masks

* Improve generation algorithm of retaking masks

* Fix device mismatch

* Adjust function signature

* Remove padding index

* Adapt ONNX exporter to new retaking mechanism
@yqzhishen
Update architecture graph
af06e30
@yqzhishen
Fix unexpected access to pitch when it is None
aba86a5
@yqzhishen
Adjust comments
801e05e
@yqzhishen
Update diagram
21d160e
@yqzhishen
Update descriptions and logging
8a818b2
@yqzhishen
Finish documentation for version 2.0.0 (#106)
608858d 
* Refactor README

* Delete old docs

* Adjust diagram

* Update image in README.md

* Add images

* Update references

* Update README.md

* Finish GettingStarted.md

* Remove redundant paragraph

* Remove docs

* Remove images

* Remove unused images

* Add link to Releases

* Add link to discord server

* Add explanations to the configuration system

* Add custom dictionary guidelines

* Server -> server

* Add performance tuning guidelines
@yqzhishen
Adjust docs
d6a5add
@yqzhishen
Update discord server link
dae6b82
@yqzhishen
Data distributed -> distributed data
cdcfb88
@yqzhishen
Add phoneme coverage checks to variance binarizer
9fcfd2e
@yqzhishen
Remove dataset making pipeline from this repository
a7210f9
@yqzhishen
Merge branch 'refactor-v2' of https://github.com/openvpi/DiffSinger i…
bdc9d67 
…nto refactor-v2
@yqzhishen
Add MIDI distribution summary to variance binarizer
cd26ecb
@yqzhishen
Support spk mix in variance exporter
b658499
@yqzhishen
Add missing forward argument
5036ab3
@yqzhishen
Adjust configurations
dc1e264
@yqzhishen
Force spk to be None for single speaker models
c71c93a
@yqzhishen
Fix crash when folder contains illegal ckpt filenames
8f3b6db
@yqzhishen
Change diff accelerator in ONNX to DDIM
e94e14e
@yqzhishen
Change default diff accelerator to DDIM
cfea3ea
@yqzhishen
Add configuration templates
bae626f
@yqzhishen
Support variance models in drop_spk.py
a2e388d
@yqzhishen
Update .gitignore
3d1a857
@yqzhishen
Merge branch 'main' into refactor-v2
39faefe
@yqzhishen
yqzhishen marked this pull request as ready for review July 16, 2023 14:54
@yqzhishen
yqzhishen merged commit 03c1bdf into main Jul 16, 2023
@yqzhishen
yqzhishen deleted the refactor-v2 branch August 4, 2023 11:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

Version 2.0.0

Development

Successfully merging this pull request may close these issues.

Tracing: deep refactoring of codebase and migration to new PyTorch & Lightning frameworks

4 participants

@yqzhishen @hrukalive @ms903x1 @yxlllc
Morty Proxy This is a proxified and sanitized view of the page, visit original site.